检索结果-内蒙古大学图书馆

Blur CLIP Context Model-Based image coding for Machines Framework With Down and Up Sample Pairs for Multitasks

IEEE ACCESS 2025年 13卷 45951-45963页

作者： Zhang, Zhongpeng Liu, Ying Santa Clara Univ Dept Comp Sci & Engn Santa Clara CA 95053 USA

image coding for Machines (ICM) aims to develop systems and frameworks for image compression and transmission tailored for computer vision tasks such as object detection and instance segmentation. This paper focuses on multi-task ICM not only for object detection and instance segmentation but also for image compression. In recent years, Contrastive Language-image Pre-training (CLIP) has demonstrated its powerful capability in extracting text and image features and has been applied to various vision tasks. Inspired by CLIP, channel-wise context model and mask convolutional neural network (PixelCNN), we propose a Blur CLIP context model (BCcm) for reducing bitrate usage and a two-hyperprior multitask framework augmented by BCcm (TMFBC). Through experiments, we have observed that down and up sample resize pairs can significantly reduce the bitrate usage. We integrated a plug-and-play down and up sample resize pair at both ends of TMFBC. Additionally, we propose a Resnet Pyramid Hierarchical Feature Extractor (RPHFE) based on down and up sample resize pairs to endow decoded images with richer multi-scale features. We term the aforementioned pipeline as TMFBC with down and up Sample Pairs (TMFBC-SP). We compare the proposed TMFBC-SP with state-of-the-art (SOTA) methods and demonstrate that we can achieve higher object detection and instance segmentation accuracy, measured by mean average precision (mAP), using fewer bitrates than existing approaches. We also compare ours with coarse-to-fine and context models on image compression, ours achieves higher PSNR and uses less bitrate.

关键词： image coding Feature extraction Codecs Object detection Context modeling Bit rate Instance segmentation Visualization Semantics Accuracy CLIP down sample image coding for machines instance segmentation object detection resize up sample

来源：评论

学校读者我要写书评

暂无评论

Guided-Wave-Based Real-Time Damage Detection in Composite Structures: A Gramian Angular Field image coding Lightweight Network Approach

引用

IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT 2025年 74卷

作者： Ma, Jitong Bao, Wenqiang Yang, Zhengyan Yang, Hongjuan Ma, Shuyi Yang, Lei Wu, Zhanjun Dalian Maritime Univ Sch Informat Sci & Technol Dalian 116026 Peoples R China Jiangnan Univ Sch Fiber Engn & Equipment Technol Wuxi 214122 Peoples R China Dalian Univ Technol Sch Aeronaut & Astronaut Dalian 116081 Peoples R China Dalian Univ Sci & Technol Sch Traff & Elect Engn Dalian 116052 Peoples R China

Ultrasonic guided wave (UGW)-based damage detection is regarded as a leading technology in structural health monitoring (SHM) for assessing the integrity of composite structures. However, achieving accurate and effective real-time damage detection remains a challenge. To address this issue, a novel UGW-based damage detection approach is proposed for real-time damage localization and quantification in composite plates. In the proposed approach, first, considering the expensive calculation of multipath UGW signals, an efficient UWG signal compression method is constructed on the basis of differential-driven piecewise aggregate approximation (DPAA) algorithm to further improve the calculation efficiency. Next, the Gramian angular field (GAF) image encoding feature extraction method is innovatively used to transform the concatenated 1-D guided wave signal into a 2-D image, which preserves the original time information and captures the temporal correlation between different timestamps in the guided wave signal. Then, by incorporating the specially designed partial group convolution (PGC) block and dynamic multiscale residual channel attention (DMRCA) mechanism, the proposed lightweight PGC-DMRCA network is capable of detecting damage in real-time with high accuracy and low computational complexity. Notably, the performance of the proposed lightweight network is verified using two real-world datasets and a publicly available dataset. Experimental results demonstrate that the proposed lightweight approach delivers exceptional performance in locating and quantifying damage, surpassing mainstream end-to-end damage detection methodologies in both accuracy and efficiency.

关键词： Real-time systems Accuracy Feature extraction Convolution image coding Sensors Location awareness Correlation Monitoring Computational complexity Attention composite structure guided wave lightweight network real-time damage detection

来源：评论

学校读者我要写书评

暂无评论

The Gap Between Principle and Practice of Lossy image coding

arXiv

引用

arXiv 2025年

作者： Zhang, Haotian Liu, Dong MOE Key Laboratory of Brain-Inspired Intelligent Perception and Cognition University of Science and Technology of China Hefei230093 China

Lossy image coding is the art of computing that is principally bounded by the image’s rate-distortion function. This bound, though never accurately characterized, has been approached practically via deep learning technologies in recent years. Indeed, learned image coding schemes allow direct optimization of the joint rate-distortion cost, thereby outperforming the handcrafted image coding schemes by a large margin. Still, it is observed that there is room for further improvement in the rate-distortion performance of learned image coding. In this article, we identify the gap between the ideal rate-distortion function forecasted by Shannon’s information theory and the empirical rate-distortion function achieved by the state-of-the-art learned image coding schemes, revealing that the gap is incurred by five different effects: modeling effect, approximation effect, amortization effect, digitization effect, and asymptotic effect. We design simulations and experiments to quantitively evaluate the last three effects, which demonstrates the high potential of future lossy image coding technologies. Copyright © 2025, The Authors. All rights reserved.

关键词： image coding

来源：评论

学校读者我要写书评

暂无评论

Semantic Prior-Guided Scalable image coding

Semantic Prior-Guided Scalable Image Coding

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Wuzhen Shi Wennan Yin Fei Tao Yang Wen Guangdong Province Engineering Laboratory for Digital Creative Technology College of Electronics and Information Engineering Shenzhen University Shenzhen China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

We propose a semantic priori-guided scalable image coding method for simultaneously supporting fast machine vision analysis and high quality human visual experience. To obtain high-performance machine vision analysis results with a more compact base layer bitrate, our base layer directly encodes intermediate semantic features of the pre-trained machine vision task network, which effectively reduces the impact of the information needed for the human vision task. To improve model performance while quickly supporting machine vision tasks, we use structural re-parameterization technology to optimize the model. Considering that the base layer’s semantic features can effectively reflect the regions of important image content, we use the semantic prior provided by the base layer to guide the enhancement layer encoding and decoding, which allows us to pay more attention to the reconstruction of semantically important regions. In addition, we use the base layer features to predict the enhancement layer features for performing feature-domain residual coding, which further reduces the bitrate and also reduces the effect of noise compared to pixel-domain residual coding. Extensive experimental results show that our method achieves significant advantages in both object detection performance and image reconstruction tasks compared with BPG and state-of-the-art deep learning-based scalable image coding methods.

关键词： Deep learning Visualization image coding Machine vision Semantics Bit rate Noise Object detection Speech processing image reconstruction

来源：评论

学校读者我要写书评

暂无评论

image-coding USING VECTOR QUANTIZATION - A REVIEW

引用

IEEE TRANSACTIONS ON COMMUNICATIONS 1988年第8期36卷 957-971页

作者： NASRABADI, NM KING, RA UNIV LONDON IMPERIAL COLL SCI & TECHNOL DEPT ELECT ENGNLONDON SW7 2AZENGLAND

A review of vector quantization techniques used for encoding digital images is presented. First, the concept of vector quantization is introduced, then its application to digital images is explained. Spatial, predictive, transform, hybrid, binary, and subband vector quantizers are reviewed. The emphasis is on the usefulness of the vector quantization when it is combined with conventional image coding techniques, or when it is used in different domains.< >

关键词： image coding Vector quantization Bit rate Signal processing algorithms Digital images image storage Pulse modulation Transform coding Acoustic signal processing Multidimensional signal processing

来源：评论

学校读者我要写书评

暂无评论

image-coding USING 2-D SPACE-VARYING LINEAR PREDICTIVE FILTERS EXCITED BY A 2-D MULTIPULSE FIELD

引用

SIGNAL PROCESSING 1989年第1期16卷 13-19页

作者： BARLAUD, M BLANCFERAUD, L MENEZ, J MATHIEU, P Laboratoire Signaux et Systèmes 41 boulevard Napoléon III 06041 Nice Cedex France

This paper deals with information compression for digitized image encoding. Among the different techniques, we discuss the Linear Predictive coding (LPC) technique. Because of the non-homogeneous nature of images, a space-varying model would yield better results. Therefore, we propose a Linear Predictive image coding technique using a space-varying 2-D AR filter. Compression is achieved by an approximation of the AR model input (prediction residual) with a limited number of pulses. The multipulse techniques of Atal and Depreterre are used for the input estimation. First, the space-varying AR 2-D filter is presented for image modeling. Using space basis functions, the LPC parameters are estimated. Then, the problem of the estimation of the synthetic input (location and amplitude of pulses) is stated. Two solutions are given to overcome the computational difficulties that arise when excitation estimation methods (Atal and Depreterre) are applied with a space-varying image model. The efficiency of the proposed solutions is shown by experimental results. Zusammenfassung Dieser Beitrag beschäftigt sich mit der Informationskompression für die Decodierung von digitalisierten Bildern. Von den verschiedenen Techniken besprechen wir die Lineare Prädiktive Codierung (LPC). Wegen der nichthomogenen Eigenschaft von Bildern, würde ein ortsabhängiges Modell zu besseren Resultaten führen. Basierend auf dieser Feststellung, schlagen wir eine Lineare Prädiktive Bildcodierungstechnik vor, die ein ortsvariantes 2-D AR Filter benutzt. Die Kompression wird durch eine Approximation des AR Modelleingangs (prediction residual) mit einer begrenzten Anzahl von Pulsen erreicht. Die Multipulse-Techniken von Atal und Depreterre werden zur Schätzung des Eingangs benutzt. Zunächst werden ortsvariante AR 2-D Filter für die Bildmodellierung vorgestellt. Unter der Benutzung von örtlichen Basisfunktionen werden die LPC Parameter geschätzt. In einem weiteren Schritt wird das Problem der Schätzung des s

关键词： image coding Linear Predictive coding multipulse excitation field space-varying 2-D filter non-stationary AR model

来源：评论

学校读者我要写书评

暂无评论

image coding based on wavelet feature vector

引用

INTERNATIONAL JOURNAL OF IMAGING SYSTEMS AND TECHNOLOGY 2005年第2期15卷 123-130页

作者： Lin, SD Shie, SC Lee, KY Natl Dong Hwa Univ Dept Comp Sci & Informat Engn Hualien Taiwan

In this article, an efficient image coding scheme that takes advantages of feature vector in wavelet domain is proposed. First, a multi-stage discrete wavelet transform is applied on the image. Then, the wavelet feature vectors are extracted from the wavelet-decomposed subimages by collecting the corresponding wavelet coefficients. And finally, the image is coded into bit-stream by applying vector quantization (VQ) on the extracted wavelet feature vectors. In the encoder, the wavelet feature vectors are encoded with a codebook where the dimension of codeword is less than that of wavelet feature vector. By this way, the coding system can greatly improve its efficiency. However, to fully reconstruct the image, the received indexes in the decoder are decoded with a codebook where the dimension of codeword is the same as that of wavelet feature vector. Therefore, the quality of reconstructed images can be preserved well. The proposed scheme achieves good compression efficiency by the following three methods. (1) Using the correlation among wavelet coefficients. (2) Placing different emphasis on wavelet coefficients at different decomposing levels. (3) Preserving the most important information of the image by coding the lowest-pass sub-image individually. In our experiments, simulation results show that the proposed scheme outperforms the recent VQ-based image coding schemes and wavelet-based image coding techniques, respectively. Moreover, the proposed scheme is also suitable for very low bit rate image coding. (c) 2005 Wiley Periodicals, Inc.

关键词： image coding discrete wavelet transformation wavelet feature vector vector quantization

来源：评论

学校读者我要写书评

暂无评论

image coding with geometric wavelets

引用

IEEE TRANSACTIONS ON image PROCESSING 2007年第1期16卷 69-77页

作者： Alani, Dror Averbuch, Amir Dekel, Shai Tel Aviv Univ Sch Comp Sci IL-69978 Tel Aviv Israel GE Healthcare IL-60408 Or Yehuda Israel

This paper describes a new and efficient method for low bit-rate image coding which is based on recent development in the theory of multivariate nonlinear piecewise polynomial approximation. It combines a binary space partition scheme with geometric wavelet (GW) tree approximation so as to efficiently capture curve singularities and provide a sparse representation of the image. The GW method successfully competes with state-of-the-art wavelet methods such as the EZW, SPIHT, and EBCOT algorithms. We report a gain of about 0.4 dB over the SPIHT and EBCOT algorithms at the bit-rate 0.0625 bits-per-pixels (bpp). It also outperforms other recent methods that are based on "sparse geometric representation." For example, we report a gain of 0.27 dB over the Bandelets algorithm at 0.1 bpp. Although the algorithm is computationally intensive, its time complexity can be significantely reduced by collecting a "global" GW n-term approximation to the image from a collection of GW trees, each constructed separately over tiles of the image.

关键词： image coding nonlinear approximation piecewise polynomial approximation sparse geometric representations wavelets and multiresolution processing

来源：评论

学校读者我要写书评

暂无评论

image coding based on classified vector quantisation using edge orientation patterns

引用

IET image PROCESSING 2017年第10期11卷 910-918页

作者： Feng, Ya-Pei Lu, Zhe-Ming Li, Hui Zhejiang Univ Sch Aeronaut & Astronaut Hangzhou 310027 Zhejiang Peoples R China Hainan Univ Coll Informat Sci & Technol Haikou 570228 Hainan Peoples R China

Vector quantisation (VQ) shows a good performance for image coding with high-compression ratios. However, there are many difficulties for image coding with VQ, especially the edge degradation and high-computational complexity. To resolve these two problems, the authors propose a new coding method based on edge orientation patterns (EOPs) by classifying image blocks into nine classes according to their edge orientations. For colour image coding, 27 codebooks (nine for each colour component) are pre-designed based on a series training images. In the encoding stage, an input colour image is decomposed into Y, Cb, and Cr components, and each component image is divided into non-overlapping 4 x 4 blocks. For each block, eight edge orientation templates of size 4 x 4 are performed to determine its edge orientation. According to the edge orientation, each block is compressed by using the corresponding codebook. Essentially, the authors' scheme is a kind of classified VC (CVQ). Simulation results show that, their EOP-based CVQ can largely improve the compression efficiency as well as speeding up the encoding process and it is sufficient to establish effectiveness of the authors' algorithm as compared with the existing techniques.

关键词： computational complexity image coding image colour analysis vector quantisation

来源：评论

学校读者我要写书评

暂无评论

image-coding ON THE PHOBOS SPACE PROBE

引用

SIGNAL PROCESSING-image COMMUNICATION 1994年第5期6卷 479-484页

作者： BASKURT, A ODET, C GOUTTE, R Laboratoire de Traitement du Signal et Ultrasons URA CNRS 1216 INSA-Lyon 20 av. A. Einstein B&acirc t. 502 69621 Villeurbanne cedex France

This paper presents the study realized for the international mission of planetary exploration Phobos II (1988) concerning the coding of Phobos images on-board. The developed software based on Discrete Cosine Transform was implemented on an on-board computer, with success, taking into account the several constraints of this space mission.

关键词： image coding DISCRETE COSINE TRANSFORM SPACE MISSION

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：